yongzx usvsnsp commited on
Commit
8b0f8b4
1 Parent(s): 191e6ce

Add Model Evals (#1)

Browse files

- Add Model Evals (220055bb494b94cca5fe6e2f9eb04ea4334f5924)


Co-authored-by: USVSN Sai Prashanth <usvsnsp@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +18 -1
README.md CHANGED
@@ -1 +1,18 @@
1
- wandb: https://wandb.ai/eleutherai/pythia-rlhf/runs/6y83ekqy?workspace=user-yongzx
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb: https://wandb.ai/eleutherai/pythia-rlhf/runs/6y83ekqy?workspace=user-yongzx
2
+
3
+ Model Evals
4
+ | Task |Version|Filter| Metric |Value | |Stderr|
5
+ |--------------|-------|------|----------|-----:|---|-----:|
6
+ |arc_challenge |Yaml |none |acc |0.2526|± |0.0127|
7
+ | | |none |acc_norm |0.2773|± |0.0131|
8
+ |arc_easy |Yaml |none |acc |0.5791|± |0.0101|
9
+ | | |none |acc_norm |0.4912|± |0.0103|
10
+ |lambada_openai|Yaml |none |perplexity|7.0516|± |0.1979|
11
+ | | |none |acc |0.5684|± |0.0069|
12
+ |logiqa |Yaml |none |acc |0.2166|± |0.0162|
13
+ | | |none |acc_norm |0.2919|± |0.0178|
14
+ |piqa |Yaml |none |acc |0.7176|± |0.0105|
15
+ | | |none |acc_norm |0.6964|± |0.0107|
16
+ |sciq |Yaml |none |acc |0.8460|± |0.0114|
17
+ | | |none |acc_norm |0.7700|± |0.0133|
18
+ |winogrande |Yaml |none |acc |0.5399|± |0.0140|